Factors Affecting the Quality of Person-Generated Wearable Device Data and Associated Challenges: Rapid Systematic Review

Beyond Step Count: Are We Ready to Use Digital Phenotyping to Make Actionable Individual Predictions in Psychiatry?

Some models for mental disorders or behaviors (eg, suicide) have been successfully developed, allowing predictions at the population level. However, current demographic and clinical variables are neither sensitive nor specific enough for making individual actionable clinical predictions. A major hope of the "Decade of the Brain" was that biological measures (biomarkers) would solve these issues and lead to precision psychiatry. However, as models are based on sociodemographic and clinical data, even when these biomarkers differ significantly between groups of patients and control participants, they are still neither sensitive nor specific enough to be applied to individual patients. Technological advances over the past decade offer a promising approach based on new measures that may be essential for understanding mental disorders and predicting their trajectories. Several new tools allow us to continuously monitor objective behavioral measures (eg, hours of sleep) and densely sample subjective measures (eg, mood). The promise of this approach, referred to as digital phenotyping, was recognized almost a decade ago, with its potential impact on psychiatry being compared to the impact of the microscope on biological sciences. However, despite the intuitive belief that collecting densely sampled data (big data) improves clinical outcomes, recent clinical trials have not shown that incorporating digital phenotyping improves clinical outcomes. This viewpoint provides a stepwise development and implementation approach, similar to the one that has been successful in the prediction and prevention of cardiovascular disease, to achieve clinically actionable predictions in psychiatry.

Mitigating data quality challenges in ambulatory wrist-worn wearable monitoring through analytical and practical approaches

Chronic disease management and follow-up are vital for realizing sustained patient well-being and optimal health outcomes. Recent advancements in wearable technologies, particularly wrist-worn devices, offer promising solutions for longitudinal patient monitoring, replacing subjective, intermittent self-reporting with objective, continuous monitoring. However, collecting and analyzing data from wearables presents several challenges, such as data entry errors, non-wear periods, missing data, and wearable artifacts. In this work, we explore these data analysis challenges using two real-world datasets (mBrain21 and ETRI lifelog2020). We introduce practical countermeasures, including participant compliance visualizations, interaction-triggered questionnaires to assess personal bias, and an optimized pipeline for detecting non-wear periods. Additionally, we propose a visualization-oriented approach to validate processing pipelines using scalable tools such as tsflex and Plotly-Resampler. Lastly, we present a bootstrapping methodology to evaluate the variability of wearable-derived features in the presence of partially missing data segments. Prioritizing transparency and reproducibility, we provide open access to our detailed code examples, facilitating adaptation in future wearable research. In conclusion, our contributions provide actionable approaches for improving wearable data collection and analysis.

Technologies for Supporting Individuals and Caregivers Living With Fetal Alcohol Spectrum Disorder: Scoping Review

Background

Fetal alcohol spectrum disorder (FASD) is a common developmental disability that requires lifelong and ongoing support but is often difficult to find due to the lack of trained professionals, funding, and support available. Technology could provide cost-effective, accessible, and effective support to those living with FASD and their caregivers.

Objective

In this review, we aimed to explore the use of technology available for supporting people living with FASD and their caregivers.

Methods

We conducted a scoping review to identify studies that included technology for people with FASD or their caregivers; focused on FASD; used an empirical study design; were published since 2005; and used technology for assessment, diagnosis, monitoring, or support for people with FASD. We searched MEDLINE, Web of Science, Scopus, Embase, APA PsycINFO, ACM Digital Library, JMIR Publications journals, the Cochrane Library, EBSCOhost, IEEE, study references, and gray literature to find studies. Searches were conducted in November 2022 and updated in January 2024. Two reviewers (CZC and HW) independently completed study selection and data extraction.

Results

In total, 17 studies exploring technology available for people with FASD showed that technology could be effective at teaching skills, supporting caregivers, and helping people with FASD develop skills.

Conclusions

Technology could provide support for people affected by FASD; however, currently there is limited technology available, and the potential benefits are largely unexplored.

Introducing a Remote Patient Monitoring Usability Impact Model to Overcome Challenges

Telehealth and remote patient monitoring (RPM), in particular, have been through a massive surge of adoption since 2020. This initiative has proven potential for the patient and the healthcare provider in areas such as reductions in the cost of care. While home-use medical devices or wearables have been shown to be beneficial, a literature review illustrates challenges with the data generated, driven by limited device usability. This could lead to inaccurate data when an exam is completed without clinical supervision, with the consequence that incorrect data lead to improper treatment. Upon further analysis of the existing literature, the RPM Usability Impact model is introduced. The goal is to guide researchers and device manufacturers to increase the usability of wearable and home-use medical devices in the future. The importance of this model is highlighted when the user-centered design process is integrated, which is needed to develop these types of devices to provide the proper user experience.

Association between heart rate variability metrics from a smartwatch and self-reported depression and anxiety symptoms: a four-week longitudinal study

Background

Elucidating the association between heart rate variability (HRV) metrics obtained through non-invasive methods and mental health symptoms could provide an accessible approach to mental health monitoring. This study explores the correlation between HRV, estimated using photoplethysmography (PPG) signals, and self-reported symptoms of depression and anxiety.

Methods

A 4-week longitudinal study was conducted among 47 participants. Time-domain and frequency-domain HRV metrics were derived from PPG signals collected via smartwatches. Mental health symptoms were evaluated using the Patient Health Questionnaire-9 (PHQ-9) and Generalized Anxiety Disorder-7 (GAD-7) at baseline, week 2, and week 4.

Results

Among the investigated HRV metrics, RMSSD, SDNN, SDSD, LF, and the LF/HF ratio were significantly associated with the PHQ-9 score, although the number of significant correlations was relatively small. Furthermore, only SDNN, SDSD and LF showed significant correlations with the GAD-7 score. All HRV metrics showed negative correlations with self-reported clinical symptoms.

Conclusions

Our findings indicate the potential of PPG-derived HRV metrics in monitoring mental health, thereby providing a foundation for further research. Notably, parasympathetically biased HRV metrics showed weaker correlations with depression and anxiety scores. Future studies should validate these findings in clinically diagnosed patients.

Quantifying the effects of sleep on sensor-derived variables from upper limb accelerometry in people with and without upper limb impairment

BACKGROUND

Despite the promise of wearable sensors for both rehabilitation research and clinical care, these technologies pose significant burden on data collectors and analysts. Investigations of factors that may influence the wearable sensor data processing pipeline are needed to support continued use of these technologies in rehabilitation research and integration into clinical care settings. The purpose of this study was to investigate the effect of one such factor, sleep, on sensor-derived variables from upper limb accelerometry in people with and without upper limb impairment and across a two-day wearing period.

METHODS

This was a secondary analysis of data collected during a prospective, longitudinal cohort study (n = 127 individuals, 62 with upper limb impairment and 65 without). Participants wore a wearable sensor on each wrist for 48 h. Five upper limb sensor variables were calculated over the full wear period (sleep included) and with sleep time removed (sleep excluded): preferred time, non-preferred time, use ratio, non-preferred magnitude and its standard deviation. Linear mixed effects regression was used to quantify the effect of sleep on each sensor variable and determine if the effect differed between people with and without upper limb impairment and across a two-day wearing period.

RESULTS

There were significant differences between sleep included and excluded for the variables preferred time (p < 0.001), non-preferred time (p < 0.001), and non-preferred magnitude standard deviation (p = 0.001). The effect of sleep was significantly different between people with and without upper limb impairment for one variable, non-preferred magnitude (p = 0.02). The effect of sleep was not substantially different across wearing days for any of the variables.

CONCLUSIONS

Overall, the effects of sleep on sensor-derived variables of upper limb accelerometry are small, similar between people with and without upper limb impairment and across a two-day wearing period, and can likely be ignored in most contexts. Ignoring the effect of sleep would simplify the data processing pipeline, facilitating the use of wearable sensors in both research and clinical practice.

Introducing the Pi-CON Methodology to Overcome Usability Deficits during Remote Patient Monitoring

The adoption of telehealth has soared, and with that the acceptance of Remote Patient Monitoring (RPM) and virtual care. A review of the literature illustrates, however, that poor device usability can impact the generated data when using Patient-Generated Health Data (PGHD) devices, such as wearables or home use medical devices, when used outside a health facility. The Pi-CON methodology is introduced to overcome these challenges and guide the definition of user-friendly and intuitive devices in the future. Pi-CON stands for passive, continuous, and non-contact, and describes the ability to acquire health data, such as vital signs, continuously and passively with limited user interaction and without attaching any sensors to the patient. The paper highlights the advantages of Pi-CON by leveraging various sensors and techniques, such as radar, remote photoplethysmography, and infrared. It illustrates potential concerns and discusses future applications Pi-CON could be used for, including gait and fall monitoring by installing an omnipresent sensor based on the Pi-CON methodology. This would allow automatic data collection once a person is recognized, and could be extended with an integrated gateway so multiple cameras could be installed to enable data feeds to a cloud-based interface, allowing clinicians and family members to monitor patient health status remotely at any time.

Wearable device adherence among insufficiently-active young adults is independent of identity and motivation for physical activity

Wearable devices are increasingly being integrated to improve prevention, chronic disease management and rehabilitation. Inferences about individual differences in device-measured physical activity depends on devices being worn long enough to obtain representative samples of behavior. Little is known about how psychological factors are associated with device wear time adherence. This study evaluated associations between identity, behavioral regulations, and device wear adherence during an ambulatory monitoring period. Young adults who reported insufficient physical activity (N = 271) were recruited for two studies before and after the SARS-COVID-19 pandemic declaration. Participants completed a baseline assessment and wore an Actigraph GT3X + accelerometer on their waist for seven consecutive days. Multiple linear regression indicated that wear time was positively associated with age, negatively associated with integrated regulation for physical activity, and greater after (versus before) the pandemic declaration. Overall, the model accounted for limited variance in device wear time. Exercise identity and exercise motivation were not associated with young adults' adherence to wearing the physical activity monitors. Researchers and clinicians can use wearable devices with young adults with minimal concern about systematic motivational biases impacting adherence to device wear.

Experiences with Wearable Sensors in Oncology during Treatment: Lessons Learned from Feasibility Research Projects in Denmark

BACKGROUND

The fraction of elderly people in the population is growing, the incidence of some cancers is increasing, and the number of available cancer treatments is evolving, causing a challenge to healthcare systems. New healthcare tools are needed, and wearable sensors could partly be potential solutions. The aim of this case report is to describe the Danish research experience with wearable sensors in oncology reporting from three oncological wearable research projects.

CASE STUDIES

Three planned case studies investigating the feasibility of different wearable sensor solutions during cancer treatment are presented, focusing on study design, population, device, aim, and planned outcomes. Further, two actual case studies performed are reported, focusing on patients included, data collected, results achieved, further activities planned, and strengths and limitations.

RESULTS

Only two of the three planned studies were performed. In general, patients found the technical issues of wearable sensors too challenging to deal with during cancer treatment. However, at the same time it was demonstrated that a large amount of data could be collected if the framework worked efficiently.

CONCLUSION

Wearable sensors have the potential to help solve challenges in clinical oncology, but for successful research projects and implementation, a setup with minimal effort on the part of patients is requested.

Wearable Sensors as a Preoperative Assessment Tool: A Review

Surgery is a common first-line treatment for many types of disease, including cancer. Mortality rates after general elective surgery have seen significant decreases whilst postoperative complications remain a frequent occurrence. Preoperative assessment tools are used to support patient risk stratification but do not always provide a precise and accessible assessment. Wearable sensors (WS) provide an accessible alternative that offers continuous monitoring in a non-clinical setting. They have shown consistent uptake across the perioperative period but there has been no review of WS as a preoperative assessment tool. This paper reviews the developments in WS research that have application to the preoperative period. Accelerometers were consistently employed as sensors in research and were frequently combined with photoplethysmography or electrocardiography sensors. Pre-processing methods were discussed and missing data was a common theme; this was dealt with in several ways, commonly by employing an extraction threshold or using imputation techniques. Research rarely processed raw data; commercial devices that employ internal proprietary algorithms with pre-calculated heart rate and step count were most commonly employed limiting further feature extraction. A range of machine learning models were used to predict outcomes including support vector machines, random forests and regression models. No individual model clearly outperformed others. Deep learning proved successful for predicting exercise testing outcomes but only within large sample-size studies. This review outlines the challenges of WS and provides recommendations for future research to develop WS as a viable preoperative assessment tool.

Digital tools to support mental health: a survey study in psychosis

BACKGROUND

There is a notable a gap between promising research findings and implementation of digital health tools. Understanding and addressing barriers to use is key to widespread implementation.

METHODS

A survey was administered to a self-selecting sample in-person (n = 157) or online (n = 58), with questions examining: i) ownership and usage rates of digital devices among people with psychosis; ii) interest in using technology to engage with mental health services; and iii) facilitators of and barriers to using digital tools in a mental healthcare context.

RESULTS

Device ownership: Virtually all participants owned a mobile phone (95%) or smartphone (90%), with Android phones slightly more prevalent than iPhones. Only a minority owned a fitness tracker (15%) or smartwatch (13%). Device ownership was significantly lower in unemployed people and those without secondary education. Device cost and paranoid ideation were barriers to ownership. Technology and mental health services: Most participants (88%) said they would willingly try a mental health app. Symptom monitoring apps were most popular, then appointment reminders and medication reminders. Half the sample would prefer an app alongside face-to-face support; the other half preferred remote support or no other mental health support. Facilitators: Participants thought using a mental health app could increase their understanding of psychosis generally, and of their own symptoms. They valued the flexibility of digital tools in enabling access to support anywhere, anytime. Barriers: Prominent barriers to using mental health apps were forgetting, lack of motivation, security concerns, and concerns it would replace face-to-face care. Overall participants reported no substantial effects of technology on their mental health, although a quarter said using a phone worsened paranoid ideation. A third used technology more when psychotic symptoms were higher, whereas a third used it less. Around half used technology more when experiencing low mood.

CONCLUSIONS

Our findings suggest rapidly increasing device ownership among people with psychosis, mirroring patterns in the general population. Smartphones appear appropriate for delivering internet-enabled support for psychosis. However, for a sub-group of people with psychosis, the sometimes complex interaction between technology and mental health may act as a barrier to engagement, alongside more prosaic factors such as forgetting.

Validated Wearable Device Shows Acute Postoperative Changes in Sleep Patterns Consistent With Patient-Reported Outcomes and Progressive Decreases in Device Compliance After Shoulder Surgery

Purpose

To assess the utility of a validated wearable device (VWD) in examining preoperative and postoperative sleep patterns and how these data compare to patient-reported outcomes (PROs) after rotator cuff repair (RCR) or total shoulder arthroplasty (TSA).

Methods

Male and female adult patients undergoing either RCR or TSA were followed up from 34 days preoperatively to 6 weeks postoperatively. Sleep metrics were collected using a VWD in an unsupervised setting. PROs were assessed using the following validated outcome measures: Patient-Reported Outcomes Measurement Information System (PROMIS) Physical Function questionnaire; American Shoulder and Elbow Surgeons self-evaluation questionnaire; visual analog scale assessing pain; and Disabilities of the Arm, Shoulder and Hand questionnaire. Data were analyzed preoperatively and at 2-week intervals postoperatively with χ2 analysis to evaluate device compliance. Sleep metrics and PROs were evaluated at each interval relative to preoperative values within each surgery type with an analysis of variance repeated on time point. The relation between sleep metrics and PROs was assessed with correlation analysis.

Results

A total of 57 patients were included, 37 in the RCR group and 20 in the TSA group. The rate of device compliance in the RCR group decreased from 84% at surgery to 46% by 6 weeks postoperatively (P < .001). Similarly, the rate of device compliance in the TSA group decreased from 81% to 52% (P < .001). Deep sleep decreased in RCR patients at 2 to 4 weeks (decrease by 10.99 ± 3.96 minutes, P = .021) and 4 to 6 weeks postoperatively (decrease by 13.37 ± 4.08 minutes, P = .008). TSA patients showed decreased deep sleep at 0 to 2 weeks postoperatively (decrease by 12.91 ± 5.62 minutes, P = .045) and increased rapid eye movement sleep at 2 to 4 weeks postoperatively (increase by 26.91 ± 10.70 minutes, P = .031). Rapid eye movement sleep in the RCR group and total sleep in the TSA group were positively correlated with more favorable PROs (P < .05).

Conclusions

VWDs allow for monitoring components of sleep that offer insight into potential targets for improving postoperative fatigue, pain, and overall recovery after shoulder surgery. However, population demographic factors and ease of device use are barriers to optimized patient compliance during data collection.

Level of Evidence

Level IV, diagnostic case series.

How Could Sensor-Based Measurement of Physical Activity Be Used in Cardiovascular Healthcare?

Physical activity and cardiovascular disease (CVD) are intimately linked. Low levels of physical activity increase the risk of CVDs, including myocardial infarction and stroke. Conversely, when CVD develops, it often reduces the ability to be physically active. Despite these largely understood relationships, the objective measurement of physical activity is rarely performed in routine healthcare. The ability to use sensor-based approaches to accurately measure aspects of physical activity has the potential to improve many aspects of cardiovascular healthcare across the spectrum of healthcare, from prediction, prevention, diagnosis, and treatment to disease monitoring. This review discusses the potential of sensor-based measurement of physical activity to augment current cardiovascular healthcare. We highlight many factors that should be considered to maximise the benefit and reduce the risks of such an approach. Because the widespread use of such devices in society is already a reality, it is important that scientists, clinicians, and healthcare providers are aware of these considerations.

Usability and ease of use of long-term remote monitoring of physical activity for individuals with acquired brain injury in community: a qualitative analysis

Introduction

Objective and continuous monitoring of physical activity over the long-term in the community is perhaps the most important step in the paradigm shift toward evidence-based practice and personalized therapy for successful community integration. With the advancement in technology, physical activity monitors have become the go-to tools for objective and continuous monitoring of everyday physical activity in the community. While these devices are widely used in many patient populations, their use in individuals with acquired brain injury is slowly gaining traction. The first step before using activity monitors in this population is to understand the patient perspective on usability and ease of use of physical activity monitors at different wear locations. However, there are no studies that have looked at the feasibility and patient perspectives on long-term utilization of activity monitors in individuals with acquired brain injury.

Methods

This pilot study aims to fill this gap and understand patient-reported aspects of the feasibility of using physical activity monitors for long-term use in community-dwelling individuals with acquired brain injury.

Results

This pilot study found that patients with acquired brain injury faced challenges specific to their functional limitations and that the activity monitors worn on the waist or wrist may be better suited in this population.

Discussion

The unique wear location-specific challenges faced by individuals with ABI need to be taken into account when selecting wearable activity monitors for long term use in this population.

Design and Implementation of an Atrial Fibrillation Detection Algorithm on the ARM Cortex-M4 Microcontroller

At present, a medium-level microcontroller is capable of performing edge computing and can handle the computation of neural network kernel functions. This makes it possible to implement a complete end-to-end solution incorporating signal acquisition, digital signal processing, and machine learning for the classification of cardiac arrhythmias on a small wearable device. In this work, we describe the design and implementation of several classifiers for atrial fibrillation detection on a general-purpose ARM Cortex-M4 microcontroller. We used the CMSIS-DSP library, which supports Naïve Bayes and Support Vector Machine classifiers, with different kernel functions. We also developed Python scripts to automatically transfer the Python model (trained in Scikit-learn) to the C environment. To train and evaluate the models, we used part of the data from the PhysioNet/Computing in Cardiology Challenge 2020 and performed simple classification of atrial fibrillation based on heart-rate irregularity. The performance of the classifiers was tested on a general-purpose ARM Cortex-M4 microcontroller (STM32WB55RG). Our study reveals that among the tested classifiers, the SVM classifier with RBF kernel function achieves the highest accuracy of 96.9%, sensitivity of 98.4%, and specificity of 95.8%. The execution time of this classifier was 720 μs per recording. We also discuss the advantages of moving computing tasks to edge devices, including increased power efficiency of the system, improved patient data privacy and security, and reduced overall system operation costs. In addition, we highlight a problem with false-positive detection and unclear significance of device-detected atrial fibrillation.

Orientation-Independent Human Activity Recognition Using Complementary Radio Frequency Sensing

RF sensing offers an unobtrusive, user-friendly, and privacy-preserving method for detecting accidental falls and recognizing human activities. Contemporary RF-based HAR systems generally employ a single monostatic radar to recognize human activities. However, a single monostatic radar cannot detect the motion of a target, e.g., a moving person, orthogonal to the boresight axis of the radar. Owing to this inherent physical limitation, a single monostatic radar fails to efficiently recognize orientation-independent human activities. In this work, we present a complementary RF sensing approach that overcomes the limitation of existing single monostatic radar-based HAR systems to robustly recognize orientation-independent human activities and falls. Our approach used a distributed mmWave MIMO radar system that was set up as two separate monostatic radars placed orthogonal to each other in an indoor environment. These two radars illuminated the moving person from two different aspect angles and consequently produced two time-variant micro-Doppler signatures. We first computed the mean Doppler shifts (MDSs) from the micro-Doppler signatures and then extracted statistical and time- and frequency-domain features. We adopted feature-level fusion techniques to fuse the extracted features and a support vector machine to classify orientation-independent human activities. To evaluate our approach, we used an orientation-independent human activity dataset, which was collected from six volunteers. The dataset consisted of more than 1350 activity trials of five different activities that were performed in different orientations. The proposed complementary RF sensing approach achieved an overall classification accuracy ranging from 98.31 to 98.54%. It overcame the inherent limitations of a conventional single monostatic radar-based HAR and outperformed it by 6%.

Context-aware electromagnetic design for continuously wearable biosymbiotic devices

Imperceptible wireless wearable devices are critical to advance digital medicine with the goal to capture clinical-grade biosignals continuously. Design of these systems is complex because of unique interdependent electromagnetic, mechanic and system level considerations that directly influence performance. Typically, approaches consider body location, related mechanical loads, and desired sensing capabilities, however, design for real world application context is not formulated. Wireless power casting eliminates user interaction and the need to recharge batteries, however, implementation is challenging because the use case influences performance. To facilitate a data-driven approach to design, we demonstrate a method for personalized, context-aware antenna, rectifier and wireless electronics design that considers human behavioral patterns and physiology to optimize electromagnetic and mechanical features for best performance across an average day of the target user group. Implementation of these methods result in devices that enable continuous recording of high-fidelity biosignals over weeks without the need for human interaction.

Recommendations for the Quality Management of Patient-Generated Health Data in Remote Patient Monitoring: Mixed Methods Study

BACKGROUND

Patient-generated health data (PGHD) collected from innovative wearables are enabling health care to shift to outside clinical settings through remote patient monitoring (RPM) initiatives. However, PGHD are collected continuously under the patient's responsibility in rapidly changing circumstances during the patient's daily life. This poses risks to the quality of PGHD and, in turn, reduces their trustworthiness and fitness for use in clinical practice.

OBJECTIVE

Using a sociotechnical health informatics lens, we developed a data quality management (DQM) guideline for PGHD captured from wearable devices used in RPM with the objective of investigating how DQM principles can be applied to ensure that PGHD can reliably inform clinical decision-making in RPM.

METHODS

First, clinicians, health information specialists, and MedTech industry representatives with experience in RPM were interviewed to identify DQM challenges. Second, these stakeholder groups were joined by patient representatives in a workshop to co-design potential solutions to meet the expectations of all the stakeholders. Third, the findings, along with the literature and policy review results, were interpreted to construct a guideline. Finally, we validated the guideline through a Delphi survey of international health informatics and health information management experts.

RESULTS

The guideline constructed in this study comprised 19 recommendations across 7 aspects of DQM. It explicitly addressed the needs of patients and clinicians but implied that there must be collaboration among all stakeholders to meet these needs.

CONCLUSIONS

The increasing proliferation of PGHD from wearables in RPM requires a systematic approach to DQM so that these data can be reliably used in clinical care. The developed guideline is an important next step toward safe RPM.

Ten Considerations for Integrating Patient-Reported Outcomes into Clinical Care for Childhood Cancer Survivors

Patient-reported outcome measures (PROMs) are subjective assessments of health status or health-related quality of life. In childhood cancer survivors, PROMs can be used to evaluate the adverse effects of cancer treatment and guide cancer survivorship care. However, there are barriers to integrating PROMs into clinical practice, such as constraints in clinical validity, meaningful interpretation, and technology-enabled administration of the measures. This article discusses these barriers and proposes 10 important considerations for appropriate PROM integration into clinical care for choosing the right measure (considering the purpose of using a PROM, health profile vs. health preference approaches, measurement properties), ensuring survivors complete the PROMs (data collection method, data collection frequency, survivor capacity, self- vs. proxy reports), interpreting the results (scoring methods, clinical meaning and interpretability), and selecting a strategy for clinical response (integration into the clinical workflow). An example framework for integrating novel patient-reported outcome (PRO) data collection into the clinical workflow for childhood cancer survivorship care is also discussed. As we continuously improve the clinical validity of PROMs and address implementation barriers, routine PRO assessment and monitoring in pediatric cancer survivorship offer opportunities to facilitate clinical decision making and improve the quality of survivorship care.

A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 1-Data From Wearable Devices

OBJECTIVES

With the emerging use of machine learning (ML) techniques, there has been particular interest in using wearable data for health economics and outcomes research (HEOR). We aimed to understand the emerging patterns of how ML has been applied to wearable data in HEOR.

METHODS

We identified studies published in PubMed between January 2016 and March 2021. Studies that included at least 1 HEOR-related Medical Subject Headings term, applied an ML, and used wearable data were eligible for inclusion. Two reviewers abstracted information including ML application types and data on which ML was applied and analyzed them using descriptive analyses.

RESULTS

A total of 148 studies were identified from PubMed, among which 32 studies met the inclusion criteria. There has been an increase over time in the number of ML studies using wearable data. ML has been more frequently used for monitoring events in real time (78%) than to predict future events (22%). There has been a wide range of outcomes examined, ranging from general physical or mental health (24%) to more disease-specific outcomes (eg, disease incidence [19%] and progression [13%]) and treatment-related outcomes (eg, treatment adherence [9%] and outcomes [9%]). Data for ML models were more often derived from wearable devices with specific medical purposes (60%) than those without (40%).

CONCLUSION

There has been a wide range of applications of ML to wearable data. Both medical and nonmedical wearable devices have been used as a data source, showing the potential for providing rich data for ML studies in HEOR.

Risk for Poor Post-Operative Quality of Life Among Wearable Use Subgroups in an All of Us Research Cohort

The objective of this research was to build and assess the performance of a prediction model for post-operative recovery status measured by quality of life among individuals experiencing a variety of surgery types. In addition, we assessed the performance of the model for two subgroups (high and moderately consistent wearable device users). Study variables were derived from the electronic health records, questionnaires, and wearable devices of a cohort of individuals with one of 8 surgery types and that were part of the NIH All of Us research program. Through multivariable analysis, high frailty index (OR 1.69, 95% 1.05-7.22, p<0.006), and older age (OR 1.76, 95% 1.55-4.08, p<0.024) were found to be the driving risk factors of poor recovery post-surgery. Our logistic regression model included 15 variables, 5 of which included wearable device data. In wearable use subgroups, the model had better accuracy for high wearable users (81%). Findings demonstrate the potential for models that use wearable measures to assess frailty to inform clinicians of patients at risk for poor surgical outcomes. Our model performed with high accuracy across multiple surgery types and were robust to variable consistency in wearable use.

Review of Internet of Things-Based Artificial Intelligence Analysis Method through Real-Time Indoor Air Quality and Health Effect Monitoring: Focusing on Indoor Air Pollution That Are Harmful to the Respiratory Organ

Everyone is aware that air and environmental pollutants are harmful to health. Among them, indoor air quality directly affects physical health, such as respiratory rather than outdoor air. However, studies that have examined the correlation between environmental and health information have been conducted with public data targeting large cohorts, and studies with real-time data analysis are insufficient. Therefore, this research explores the research with an indoor air quality monitoring (AQM) system based on developing environmental detection sensors and the internet of things to collect, monitor, and analyze environmental and health data from various data sources in real-time. It explores the usage of wearable devices for health monitoring systems. In addition, the availability of big data and artificial intelligence analysis and prediction has increased, investigating algorithmic studies for accurate prediction of hazardous environments and health impacts. Regarding health effects, techniques to prevent respiratory and related diseases were reviewed.

An interactive fitness-for-use data completeness tool to assess activity tracker data

OBJECTIVE

To design and evaluate an interactive data quality (DQ) characterization tool focused on fitness-for-use completeness measures to support researchers' assessment of a dataset.

MATERIALS AND METHODS

Design requirements were identified through a conceptual framework on DQ, literature review, and interviews. The prototype of the tool was developed based on the requirements gathered and was further refined by domain experts. The Fitness-for-Use Tool was evaluated through a within-subjects controlled experiment comparing it with a baseline tool that provides information on missing data based on intrinsic DQ measures. The tools were evaluated on task performance and perceived usability.

RESULTS

The Fitness-for-Use Tool allows users to define data completeness by customizing the measures and its thresholds to fit their research task and provides a data summary based on the customized definition. Using the Fitness-for-Use Tool, study participants were able to accurately complete fitness-for-use assessment in less time than when using the Intrinsic DQ Tool. The study participants perceived that the Fitness-for-Use Tool was more useful in determining the fitness-for-use of a dataset than the Intrinsic DQ Tool.

DISCUSSION

Incorporating fitness-for-use measures in a DQ characterization tool could provide data summary that meets researchers needs. The design features identified in this study has potential to be applied to other biomedical data types.

CONCLUSION

A tool that summarizes a dataset in terms of fitness-for-use dimensions and measures specific to a research question supports dataset assessment better than a tool that only presents information on intrinsic DQ measures.

Modulation Spectral Signal Representation for Quality Measurement and Enhancement of Wearable Device Data: A Technical Note

Wearable devices are burgeoning, and applications across numerous verticals are emerging, including human performance monitoring, at-home patient monitoring, and health tracking, to name a few. Off-the-shelf wearables have been developed with focus on portability, usability, and low-cost. As such, when deployed in highly ecological settings, wearable data can be corrupted by artifacts and by missing data, thus severely hampering performance. In this technical note, we overview a signal processing representation called the modulation spectrum. The representation quantifies the rate-of-change of different spectral magnitude components and is shown to separate signal from noise, thus allowing for improved quality measurement, quality enhancement, and noise-robust feature extraction, as well as for disease characterization. We provide an overview of numerous applications developed by the authors over the last decade spanning different wearable modalities and list the results obtained from experimental results alongside comparisons with various state-of-the-art benchmark methods. Open-source software is showcased with the hope that new applications can be developed. We conclude with a discussion on possible future research directions, such as context awareness, signal compression, and improved input representations for deep learning algorithms.

Leveraging Mobile-Based Sensors for Clinical Research to Obtain Activity and Health Measures for Disease Monitoring, Prevention, and Treatment

Clinical researchers are using mobile-based sensors to obtain detailed and objective measures of the activity and health of research participants, but many investigators lack expertise in integrating wearables and sensor technologies effectively into their studies. Here, we describe the steps taken to design a study using sensors for disease monitoring in older adults and explore the benefits and drawbacks of our approach. In this study, the Geriatric Acute and Post-acute Fall Prevention Intervention (GAPcare), we created an iOS app to collect data from the Apple Watch's gyroscope, accelerometer, and other sensors; results of cognitive and fitness tests; and participant-entered survey data. We created the study app using ResearchKit, an open-source framework developed by Apple for medical research that includes neuropsychological tests (e.g., of executive function and memory), gait speed, balance, and other health assessments. Data is transmitted via an Application Programming Interface (API) from the app to REDCap for researchers to monitor and analyze in real-time. Employing the lessons learned from GAPcare could help researchers create study-tailored research apps and access timely information about their research participants from wearables and smartphone devices for disease prevention, monitoring, and treatment.

Wearable-Based Assessment of Frailty Trajectories During Cardiac Rehabilitation After Open-Heart Surgery

Frailty in patients after open-heart surgery influences the type and intensity of a cardiac rehabilitation program. The response to tailored exercise training can be different, requiring convenient tools to assess the effectiveness of a training program routinely. The study aims to investigate whether kinematic measures extracted from the acceleration signals can provide information about frailty trajectories during rehabilitation. One hundred patients after open-heart surgery, assigned to the equal-sized intervention and control groups, participated in exercise training during inpatient rehabilitation. After rehabilitation, the intervention group continued exercise training at home, whereas the control group was asked to maintain the usual physical activity regimen. Stride time, cadence, movement vigor, gait asymmetry, Lissajous index, and postural sway were estimated during the clinical walk and stair-climbing tests before and after inpatient rehabilitation as well as after home-based exercise training. Frailty was assessed using the Edmonton frail scale. Most kinematic measures estimated during walking improved after rehabilitation along with the improvement in frailty status, i.e., stride time, cadence, postural sway, and movement vigor improved in 71%, 77%, 81%, and 83% of patients, respectively. Meanwhile, kinematic measures during stair-climbing improved to a lesser extent compared to walking. Home-based exercise training did not result in a notable change in kinematic measures which agrees well with only a negligible deterioration in frailty status. The study demonstrates the feasibility to follow frailty trajectories during inpatient rehabilitation after open-heart surgery based on kinematic measures extracted using a single wearable sensor.

Anomaly Detection Framework for Wearables Data: A Perspective Review on Data Concepts, Data Analysis Algorithms and Prospects

Wearable devices use sensors to evaluate physiological parameters, such as the heart rate, pulse rate, number of steps taken, body fat and diet. The continuous monitoring of physiological parameters offers a potential solution to assess personal healthcare. Identifying outliers or anomalies in heart rates and other features can help identify patterns that can play a significant role in understanding the underlying cause of disease states. Since anomalies are present within the vast amount of data generated by wearable device sensors, identifying anomalies requires accurate automated techniques. Given the clinical significance of anomalies and their impact on diagnosis and treatment, a wide range of detection methods have been proposed to detect anomalies. Much of what is reported herein is based on previously published literature. Clinical studies employing wearable devices are also increasing. In this article, we review the nature of the wearables-associated data and the downstream processing methods for detecting anomalies. In addition, we also review supervised and un-supervised techniques as well as semi-supervised methods that overcome the challenges of missing and un-annotated healthcare data.

Identifying Data Quality Dimensions for Person-Generated Wearable Device Data: Multi-Method Study

BACKGROUND

There is a growing interest in using person-generated wearable device data for biomedical research, but there are also concerns regarding the quality of data such as missing or incorrect data. This emphasizes the importance of assessing data quality before conducting research. In order to perform data quality assessments, it is essential to define what data quality means for person-generated wearable device data by identifying the data quality dimensions.

OBJECTIVE

This study aims to identify data quality dimensions for person-generated wearable device data for research purposes.

METHODS

This study was conducted in 3 phases: literature review, survey, and focus group discussion. The literature review was conducted following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guideline to identify factors affecting data quality and its associated data quality challenges. In addition, we conducted a survey to confirm and complement results from the literature review and to understand researchers' perceptions on data quality dimensions that were previously identified as dimensions for the secondary use of electronic health record (EHR) data. We sent the survey to researchers with experience in analyzing wearable device data. Focus group discussion sessions were conducted with domain experts to derive data quality dimensions for person-generated wearable device data. On the basis of the results from the literature review and survey, a facilitator proposed potential data quality dimensions relevant to person-generated wearable device data, and the domain experts accepted or rejected the suggested dimensions.

RESULTS

In total, 19 studies were included in the literature review, and 3 major themes emerged: device- and technical-related, user-related, and data governance-related factors. The associated data quality problems were incomplete data, incorrect data, and heterogeneous data. A total of 20 respondents answered the survey. The major data quality challenges faced by researchers were completeness, accuracy, and plausibility. The importance ratings on data quality dimensions in an existing framework showed that the dimensions for secondary use of EHR data are applicable to person-generated wearable device data. There were 3 focus group sessions with domain experts in data quality and wearable device research. The experts concluded that intrinsic data quality features, such as conformance, completeness, and plausibility, and contextual and fitness-for-use data quality features, such as completeness (breadth and density) and temporal data granularity, are important data quality dimensions for assessing person-generated wearable device data for research purposes.

CONCLUSIONS

In this study, intrinsic and contextual and fitness-for-use data quality dimensions for person-generated wearable device data were identified. The dimensions were adapted from data quality terminologies and frameworks for the secondary use of EHR data with a few modifications. Further research on how data quality can be assessed with respect to each dimension is needed.